BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:370@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20240307T140000
DTEND;TZID=Europe/Paris:20240307T140000
DTSTAMP:20260828T111454Z
URL:https://isdm.umontpellier.fr/events/sampling-through-optimization-of-d
 iscrepancies-2/
SUMMARY:Sampling through optimization of discrepancies
DESCRIPTION:Room 02.022\, Building 5\, St Priest campus\n\nMachine Learning
  in Montpellier\, Theory &amp\; Practice\n\nSampling from a target measure
  when only partial information is available (e.g. unnormalized density as 
 in Bayesian inference\, or true samples as in generative modeling ) is a f
 undamental problem in computational statistics and machine learning. The s
 ampling problem can be formulated as an optimization over the space of pro
 bability distributions of a well-chosen discrepancy (e.g. a divergence or 
 distance). In this talk\, we&#x27\;ll discuss several properties of sampli
 ng algorithms for some choices of discrepancies (well-known ones\, or nove
 l proxies)\, both regarding their optimization and quantization aspects.\,
 \,\n\nMachine Learning in Montpellier\, Theory &amp\; Practice
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/
 2026/06/ml-mtp-gC78d5.png
CATEGORIES:ML MTP
LOCATION:Saint Priest Campus - Building 5 - Room 02.022\, 860 rue St Priest
 \, Montpellier\, 
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=860 rue St Priest\, Montpel
 lier\, ;X-APPLE-RADIUS=100;X-TITLE=Saint Priest Campus - Building 5 - Room
  02.022:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20231029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR